mlsanityData to 7 Oct 2026

Student of Games: A unified learning algorithm for both perfect and imperfect information games

arXiv 2112.03178 ↗First posted 6 Dec 2021cs.AI cs.GT cs.LGcited by 22

Not on the map. Why?

Abstract (arXiv)

Games have a long history as benchmarks for progress in artificial intelligence. Approaches using search and learning produced strong performance across many perfect information games, and approaches using game-theoretic reasoning and learning demonstrated strong performance for specific imperfect information poker variants. We introduce Student of Games, a general-purpose algorithm that unifies previous approaches, combining guided search, self-play learning, and game-theoretic reasoning. Student of Games achieves strong empirical performance in large perfect and imperfect information games -- an important step towards truly general algorithms for arbitrary environments. We prove that Student of Games is sound, converging to perfect play as available computation and approximation capacity increases. Student of Games reaches strong performance in chess and Go, beats the strongest openly available agent in heads-up no-limit Texas hold'em poker, and defeats the state-of-the-art agent in Scotland Yard, an imperfect information game that illustrates the value of guided search, learning, and game-theoretic reasoning.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Builds on 27 of its 76 references that are in the map. First posted on arXiv 6 Dec 2021.

Builds on

27 of 76 references.

References · 27

  1. 2017DeepStack: Expert-Level Artificial Intelligence in No-Limit Pokercited by 228
  2. 2019The Hanabi Challenge: A New Frontier for AI Researchcited by 194
  3. 2019OpenSpiel: A Framework for Reinforcement Learning in Gamescited by 180
  4. 2021Collaborating with Humans without Human Datacited by 139
  5. 2020Combining Deep Reinforcement Learning and Search for Imperfect-Information Gamescited by 110
  6. 2018Deep Counterfactual Regret Minimizationcited by 102
  7. 2018Bayesian Action Decoder for Deep Multi-Agent Reinforcement Learningcited by 67
  8. 2020From Poincar'e Recurrence to Convergence in Imperfect Information Games: Finding Equilibrium via Regularizationcited by 59
  9. 2017Safe and Nested Subgame Solving for Imperfect-Information Gamescited by 39
  10. 2020DREAM: Deep Regret minimization with Advantage baselines and Model-free learningcited by 36
  11. 2018Actor-Critic Policy Optimization in Partially Observable Multiagent Environmentscited by 35
  12. 2019Rethinking Formal Models of Partially Observable Multiagent Decision Makingcited by 35
15 more
  1. 2021XDO: A Double Oracle Algorithm for Extensive-Form Gamescited by 34
  2. 2019Improving Policies via Search in Cooperative Partially Observable Gamescited by 33
  3. 2019Computing Approximate Equilibria in Sequential Adversarial Games by Exploitability Descentcited by 31
  4. 2021No-Press Diplomacy from Scratchcited by 31
  5. 2013Solving Imperfect Information Games Using Decompositioncited by 27
  6. 2020Learning to Play No-Press Diplomacy with Best Response Policy Iterationcited by 25
  7. 2020The Advantage Regret-Matching Actor-Criticcited by 17
  8. 2018Double Neural Counterfactual Regret Minimizationcited by 16
  9. 2021Solving Common-Payoff Games with Approximate Policy Iterationcited by 15
  10. 2016AIVAT: A New Variance Reduction Technique for Agent Evaluation in Imperfect Information Gamescited by 8
  11. 2020Unlocking the Potential of Deep Counterfactual Value Networkscited by 8
  12. 2021Search in Imperfect Information Gamescited by 8
  13. 2018Monte Carlo Continual Resolving for Online Strategy Computation in Imperfect Information Gamescited by 7
  14. 2020Human-Agent Cooperation in Bridge Biddingcited by 7
  15. 2020Sound Algorithms in Imperfect Information Gamescited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 1; 2024: 5; 2025: 8; 2026: 7.

22 papers.

Sort:

By area:

  1. 2024Human vs. Machine: Behavioral Differences Between Expert Humans and Language Models in Wargame Simulationscited by 20
  2. 2022Sample-Efficient Learning of Correlated Equilibria in Extensive-Form Gamescited by 7
  3. 2025General search techniques without common knowledge for imperfect-information games, and application to superhuman Fog of War chesscited by 5
  4. 2025Human-Level Competitive Pok'emon via Scalable Offline Reinforcement Learning with Transformerscited by 4
  5. 2025Cardiverse: Harnessing LLMs for Novel Card Game Prototypingcited by 2
  6. 2024Configurable Mirror Descent: Towards a Unification of Decision Makingcited by 1
  7. 2025Modeling Uncertainty: Constraint-Based Belief States in Imperfect-Information Gamescited by 1
  8. 2025Look-ahead Reasoning with a Learned Model in Imperfect Information Gamescited by 1
  9. 2026AV-AIVAT: 74x Cheaper Agent Evaluation with Certified Anytime-Valid Stopping in Imperfect-Information Gamescited by 1
  10. 2023AI planning in the imagination: High-level planning on learned abstract search spacescited by 0
  11. 2024State-Constrained Zero-Sum Differential Games with One-Sided Informationcited by 0
  12. 2024HSVI-based Online Minimax Strategies for Partially Observable Stochastic Games with Neural Perception Mechanismscited by 0
10 more
  1. 2024GPU-Accelerated Counterfactual Regret Minimizationcited by 0
  2. 2025Meta-Learning in Self-Play Regret Minimizationcited by 0
  3. 2025Neural Bayesian Filteringcited by 0
  4. 2025Outbidding and Outbluffing Elite Humans: Mastering Liar's Poker via Self-Play and Reinforcement Learningcited by 0
  5. 2026SkyNet: Belief-Aware Planning for Partially-Observable Stochastic Gamescited by 0
  6. 2026Self-Play Reinforcement Learning under Imperfect Information in Big 2cited by 0
  7. 2026Coachable agents for interactive gameplaycited by 0
  8. 2026PokaiTrainer: Scaling Equilibrium Search to Competitive Pok'emon VGCcited by 0
  9. 2026Unsound Search with Policy and Value Networks in Legends of Code and Magiccited by 0
  10. 2026GPU-CFR: 80x Faster Counterfactual Regret Minimization by Compiling the Game to Static Dataflow and CUDA Graph Replaycited by 0